Simulate neural network – MATLAB sim

Description

sim simulates neural networks.

[Y,Xf,Af] = sim(net,X,Xi,Ai,T) takes

net

Network

X

Network inputs

Xi

Initial input delay conditions (default = zeros)

Ai

Initial layer delay conditions (default = zeros)

T

Network targets (default = zeros)

and returns

Y

Network outputs

Xf

Final input delay conditions

Af

Final layer delay conditions

sim is usually called implicitly by calling the neural network as a
function. For instance, these two expressions return the same result:

y = sim(net,x,xi,ai)
y = net(x,xi,ai)

Note that arguments Xi, Ai, Xf,
and Af are optional and need only be used for networks that have input or
layer delays.

The signal arguments can have two formats: cell array or matrix.

The cell array format is easiest to describe. It is most convenient for networks with
multiple inputs and outputs, and allows sequences of inputs to be presented:

X

Ni-by-TS cell array

Each element X{i,ts} is an
Ri-by-Q matrix.

Xi

Ni-by-ID cell array

Each element Xi{i,k} is an
Ri-by-Q matrix.

Ai

Nl-by-LD cell array

Each element Ai{i,k} is an
Si-by-Q matrix.

T

No-by-TS cell array

Each element X{i,ts} is a
Ui-by-Q matrix.

Y

No-by-TS cell array

Each element Y{i,ts} is a
Ui-by-Q matrix.

Xf

Ni-by-ID cell array

Each element Xf{i,k} is an
Ri-by-Q matrix.

Af

Nl-by-LD cell array

Each element Af{i,k} is an
Si-by-Q matrix.

where

Ni = net.numInputsNl = net.numLayersNo = net.numOutputsID = net.numInputDelaysLD = net.numLayerDelaysTS =

Number of time steps

Q =

Batch size

Ri = net.inputs{i}.sizeSi = net.layers{i}.sizeUi = net.outputs{i}.size

The columns of Xi, Ai, Xf, and
Af are ordered from oldest delay condition to most recent:

Xi{i,k}=

Input i at time ts = k -
ID

Xf{i,k}=

Input i at time ts = TS + k -
ID

Ai{i,k}=

Layer output i at time ts = k -
LD

Af{i,k}=

Layer output i at time ts = TS + k -
LD

The matrix format can be used if only one time step is to be simulated (TS
= 1). It is convenient for networks with only one input and output, but can also
be used with networks that have more.

Each matrix argument is found by storing the elements of the corresponding cell array
argument in a single matrix:

X

(sum of Ri)-by-Q matrix

Xi

(sum of Ri)-by-(ID*Q)
matrix

Ai

(sum of Si)-by-(LD*Q)
matrix

T

(sum of Ui)-by-Q matrix

Y

(sum of Ui)-by-Q matrix

Xf

(sum of Ri)-by-(ID*Q)
matrix

Af

(sum of Si)-by-(LD*Q)
matrix

[Y,Xf,Af] = sim(net,{Q TS},Xi,Ai) is used for networks that do not
have an input when cell array notation is used.

[Y,...] = sim(net,...,'useParallel',...),
[Y,...]
= sim(net,...,'useGPU',...), or
[Y,...] = sim(net,...,'showResources',...) (or the network called as a
function) accepts optional name/value pair arguments to control how calculations are performed.
Two of these options allow training to happen faster or on larger datasets using parallel
workers or GPU devices if Parallel Computing Toolbox is available. These are the optional
name/value pairs:

'useParallel','no'

Calculations occur on normal MATLAB thread. This is the default
'useParallel' setting.

'useParallel','yes'

Calculations occur on parallel workers if a parallel pool is open. Otherwise
calculations occur on the normal MATLAB thread.

'useGPU','no'

Calculations occur on the CPU. This is the default ‘useGPU’
setting.

'useGPU','yes'

Calculations occur on the current gpuDevice if it is a supported GPU (See
Parallel Computing Toolbox for GPU requirements.) If the current gpuDevice is not
supported, calculations remain on the CPU. If 'useParallel' is also
'yes' and a parallel pool is open, then each worker with a unique GPU
uses that GPU, other workers run calculations on their respective CPU cores.

'useGPU','only'

If no parallel pool is open, then this setting is the same as
'yes'. If a parallel pool is open, then only workers with unique GPUs
are used. However, if a parallel pool is open, but no supported GPUs are available, then
calculations revert to performing on all worker CPUs.

'showResources','no'

Do not display computing resources used at the command line. This is the default
setting.

'showResources','yes'

Show at the command line a summary of the computing resources actually used. The
actual resources may differ from the requested resources, if parallel or GPU computing is
requested but a parallel pool is not open or a supported GPU is not available. When
parallel workers are used, each worker’s computation mode is described, including workers
in the pool that are not used.

[Ycomposite,...] = sim(net,Xcomposite,...) takes Composite data and
returns Composite results. If Composite data is used, then 'useParallel' is
automatically set to 'yes'.

[Ygpu,...] = sim(net,Xgpu,...) takes gpuArray data and returns
gpuArray results. If gpuArray data is used, then 'useGPU' is automatically
set to 'yes'.